Role:
Sole designer & engineer
Ships as:
Single Docker container
Status:
Private beta
Basilisk
A full, OpenAI-compatible LLM server in a single Docker container. Chat, completions, time-series analysis and anomaly scoring, running locally with no cloud bills and complete control of your data.
- Applied AI
- Self-hosted
- Docker
Drop it on any machine, laptop, server or edge device, and you have OpenAI-compatible chat and completion endpoints, plus time-series database analysis and anomaly scoring. No cloud, no per-token fees, no data leaving your network.
Chat & completions
A drop-in OpenAI-compatible API. Use it with LangChain, LlamaIndex, your own scripts or any existing OpenAI client, just change the base URL.
Time-series analysis
Native integration with VictoriaMetrics, Prometheus and other time-series databases, so you can ask natural-language questions about your metrics.
Anomaly scoring
Anomaly detection on time-series data, using the LLM together with statistical models, giving scored alerts with plain-English explanations.
Simple to run
One command. Works on x86-64 and ARM: laptops, servers, Kubernetes, even a Raspberry Pi.
Private by design
Your data never leaves your infrastructure, which suits sensitive environments, regulated industries and anyone tired of cloud bills.
Model-flexible
Works with any GGUF model (Llama 3, Mistral, Phi, Gemma and more), swapped by changing one environment variable.